llmf

Free, keyless LLM access in one call — with automatic multi-provider fallback.

llmf (llmfree) is a stdlib-only Python library and CLI for public, no-API-key OpenAI-compatible endpoints. It picks a live target, falls back on failure, and runs on desktop and Termux.

import llmf

r = llmf.chat("Explain the CAP theorem in two sentences.")
print(r)                 # Reply is a str subclass
print(r.source)          # "provider/model"
print(r.provider, r.model, round(r.latency, 3), r.usage)

Install

pip install -U llmf
pip install -U "llmf[stealth]"   # optional: curl_cffi TLS fingerprint

python -c "import llmf; print(llmf.__version__)"
llmf version
llmf -v version                  # + active transport

pip show llmf

Name: llmf
Version: 0.6.2
Summary: free, keyless LLM chat with automatic multi-provider fallback — stdlib only
Home-page: https://github.com/MoonLite-Br/llmfree
Author: Html
License: MIT
Requires-Python: >=3.8
Requires: (none)

Python API

Short form → Reply

import llmf

r = llmf.chat("Hello!")
r.text, r.source, r.provider, r.model, r.latency, r.usage, r.attempts

llmf.chat("hi", model="best")          # fast | best | code | vision | reasoning
llmf.chat("hi", model=["best", "fast"])
llmf.chat("hi", provider="ch-at")
llmf.chat("hi", provider="nottrack")   # opt-in (auto=False)
llmf.chat("Describe this", images=["photo.jpg"], model="vision")

for piece in llmf.stream("Count 1 to 5"):
    print(piece, end="", flush=True)

OpenAI-shaped form

from llmf import LLMF

llm = LLMF()
c = llm.chat.completions.create(
    model="best",
    messages=[{"role": "user", "content": "Hello"}],
)
print(c.choices[0].message.content)
print(c.model, c.provider, c.usage, c.latency)

Catalog, survival, concurrency, transport

for m in llmf.models.list():
    print(m.name, m.tags, m.alive, m.samples, m.streaming)

llmf.models.list(live=True)
llmf.models.resolve("fast")
llmf.models.check()                 # doctor → survival history

llmf.configure(
    timeout=30,
    vision_timeout=90,
    routing="adaptive",
    race=2,
    max_inflight=6,                 # per-provider parallel cap before spill
    transport="auto",               # urllib | auto | curl_cffi
    impersonate="chrome",
)
llmf.register("lab", "http://localhost:11434/v1", ["llama3"], front=True)

Env: LLMF_TIMEOUT, LLMF_PROXY, LLMF_MODEL, LLMF_ROUTING, LLMF_TRANSPORT, LLMF_IMPERSONATE

What’s new (0.6.x)

0.6.2

• Packaging release of the load-aware stack with full README / correct project URLs / static badges.

0.6.1 (runtime)

• Load-aware routing (threads, race, llmf serve): per-provider concurrency caps (Client(max_inflight=6); e.g. ch-at 8, llm7 3, pollinations 1). Extra work spills to the next provider instead of queueing behind a busy one.
• llmf serve --max-concurrent N (default 48): returns 429 {"code":"busy"} + Retry-After: 1 under load; listen backlog 128.
• Friendlier errors for llmf serve --host 8000 (port-in-host-slot) and “port in use”.

0.6.0

• Vetted catalogue (≥2 live runs, ≥75% success).
• Survival history (history.json, alive / flaky / dead, ModelInfo.alive / .samples).
• Optional llmf[stealth] / transport / impersonate.
• ModelInfo.streaming / no-stream in llmf models.

See CHANGELOG.md.

Built-in providers

CLI

llmf "question" | llmf ask "…"
llmf chat
llmf models [list|check|resolve NAME]
llmf doctor [--all] [--include-non-chat] [--include-limited] [--no-save]
llmf providers | health | version
llmf serve [--host] [--port] [--max-concurrent N] [--api-key] [--cors]

Flags: -m/--model, -p/--provider, -s/--system, --image, --stream, --json, -v,
--routing ranked|adaptive, --race N, --timeout, --proxy,
--transport urllib|auto|curl_cffi, --impersonate,
--live, --all, --include-limited, --include-non-chat, --no-save,
serve: --host, --port, --max-concurrent, --api-key, --cors, --strict-models, --no-fallback.

$ llmf -v "2+2=?"
$ llmf models
$ llmf doctor
$ llmf serve --port 8000 --max-concurrent 48
$ llmf --transport auto -v version

Behaviour

• Fallback + cooldowns; survival scores demote flaky models.
• Load-aware: at concurrency limit, spill to next provider (no long queue on one busy endpoint).
• Live catalog/doctor: chat+free by default.
• transport="auto" uses curl_cffi when llmf[stealth] is installed.
• Total failure → llmf.AllProvidersFailed.

Safety

Unofficial free endpoints may change. Do not send secrets. Opt-in providers and discover() are explicit. llmf serve defaults to localhost.

Development

git clone https://github.com/MoonLite-Br/llmfree.git
cd llmfree
python -m unittest discover -s tests -v
python -m build && twine check dist/*

License

MIT © 2026 Html / MoonLite-Br